Chinese character recognition software OCR application II

1. Image processing module

The image processing module mainly has the functions of document scanning, image scaling, image rotation and the like. After input through the scanner, the document forms an image file, and the image processing module can enlarge the image to remove stains and scratches. If the image rotates incorrectly, the image can be manually or automatically rotated in order to create better conditions for character recognition. Higher recognition rate.

2. Layout division module

The layout division module mainly includes layout division and change division, that is, understanding of the layout, word segmentation, normalization, etc., and can be selected automatically or manually. The purpose is to tell the OCR software to separate the articles, forms, etc. of the same layout so that they can be processed separately and in what order.

3. Character Recognition Module

The character recognition module is the core part of the OCR software, a simple text recognition process diagram, as shown below. The character recognition module mainly "reads" the input Chinese characters, but it cannot be read one line at a time. It must be cut line by line. For Chinese characters, it is usually recognized one word at a time, that is, single character recognition, and then normalization. The character recognition module extracts features of different sample Chinese characters, completes recognition, automatically finds suspicious characters, and has functions such as front and rear associations.

Scan input original → line cutting → word cutting → naturalization → recognition feature extraction → word recognition ------┐
└-→ pre-classification feature extraction → feature library (dictionary) → output manuscript

4. Text editing module

The text editing module mainly modifies and edits the OCR-recognized text. If the system recognizes that it is incorrect, the text is displayed in bold red or blue, and similar text is provided for selection, and the editor is selected for output.

How to use OCR software

Although there are many types of OCR software, their usage is much the same. The first thing to do is scan the document and then perform OCR recognition. The OCR software is used as follows:

1. Document scanning

In order to use OCR software for character recognition, documents can be scanned directly in the OCR software. After running the OCR software, the OCR software interface appears. If you use the Crystal OCR, you will see the window shown in Figure 3.

Place the document to be scanned on the glass surface of the scanner so that the side to be scanned faces the glass surface of the scanner with the upper end of the document facing down, aligning with the edge of the scale, and then cover the scanner to prepare for scanning. Click the "Scan" button in the window to enter the scan driver software for scanning. The scanning method is not described here. However, it should be noted that the resolution can be set at 200 to 400 dpi. For text documents, adjusting the brightness is critical. The scanned document image appears in the OCR software window, as shown in Figure 4.

2. OCR recognition

For ease of operation, options can be selected from the menu, various icons appear on the left side of the window, see FIG.

For better use, first of all, from the top down to introduce the icon on the left side of the screen:

Zoom tool: used to enlarge the image; Zoom out tool: to reduce the image; Set Recognition Area tool: to set the recognition area; Set Recognition Order tool: to set the recognition order; Delete Recognition Area tool: used to delete the recognition area; Erase Image Noise tool: used to erase an area in the image; Rotate Image tool: used to rotate the image by 90°, 180° or 270°; Tilt Correction tool: Used for manual image tilt correction.

General steps for OCR recognition:

(1) After the document is scanned, the text screen to be recognized that appears in the window is very small. First select the “Enlarge” tool and enlarge the screen appropriately to make the screen look more clearly. If necessary, you can also select the "zoom out" tool to narrow the screen appropriately.

(2) If the screen needs to be rotated 90°, 180°, or 270°, use the Rotate Image tool to rotate the image. If the text screen is slanted, you can select the "tilt correction" tool to correct the picture.

(3) Select the “Set Recognition Area” tool when identifying, and frame the area to be identified on the text screen. You can also frame multiple areas according to the screen conditions. If there is an error in the framed area, you can delete the selected area by using the Delete Recognition Area tool.

(4) In order to improve the recognition rate, if the selected identification area has noise or an unrecognized image, the “Erase Image Noise” tool can be selected to erase the noise little by little. If you need to erase in slices, you can select the Wipe Image Block tool.

(5) Click "identify" icon, then OCR display text segmentation is ongoing, and then transferred to the "identification" screen, the text will be gradually recognized, and then transferred to the "Document proofing" window shown in Figure 5.

Many OCR softwares have text editing functions and are recognized as having potentially erroneous text that is displayed in bright colors and can be modified.

(6) Store the identified file as a text (TXT) file or a Word RTF file.